{"id":"https://openalex.org/W4405787186","doi":"https://doi.org/10.1109/iros58592.2024.10801291","title":"GRID: Scene-Graph-based Instruction-driven Robotic Task Planning","display_name":"GRID: Scene-Graph-based Instruction-driven Robotic Task Planning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405787186","doi":"https://doi.org/10.1109/iros58592.2024.10801291"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113002178","display_name":"Zhe Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhe Ni","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoxin Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxin Deng","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014897885","display_name":"Cong Tai","orcid":"https://orcid.org/0009-0000-6803-4088"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Tai","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024348692","display_name":"Xinyue Zhu","orcid":"https://orcid.org/0000-0001-7967-1066"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Zhu","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001322","display_name":"Qiang Xie","orcid":"https://orcid.org/0009-0000-6538-7742"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghongbing Xie","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069672866","display_name":"Weihang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihang Huang","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389075","display_name":"Xiang Wu","orcid":"https://orcid.org/0000-0002-9642-8743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Wu","raw_affiliation_strings":["Shenzhen Pudu Technology Inc.,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Pudu Technology Inc.,Shenzhen,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029947227","display_name":"Long Zeng","orcid":"https://orcid.org/0000-0003-4968-1401"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zeng","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5113002178"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.1435,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95307564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13765","last_page":"13772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8094905018806458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6295517683029175},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6240796446800232},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4899732172489166},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4579834043979645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43320903182029724},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.409205824136734},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3645351827144623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36050838232040405},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1770525872707367},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09234693646430969},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09190058708190918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094905018806458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6295517683029175},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6240796446800232},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4899732172489166},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4579834043979645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43320903182029724},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.409205824136734},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3645351827144623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36050838232040405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1770525872707367},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09234693646430969},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09190058708190918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2963660226","https://openalex.org/W2990129662","https://openalex.org/W3003205975","https://openalex.org/W3034758614","https://openalex.org/W3035154952","https://openalex.org/W3039925688","https://openalex.org/W3119206490","https://openalex.org/W3183042936","https://openalex.org/W3192660112","https://openalex.org/W3207057769","https://openalex.org/W4224912544","https://openalex.org/W4226054716","https://openalex.org/W4285218426","https://openalex.org/W4297903107","https://openalex.org/W4312732547","https://openalex.org/W4322704425","https://openalex.org/W4383109478","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4385570594","https://openalex.org/W4385876383","https://openalex.org/W4386076183","https://openalex.org/W4390873239","https://openalex.org/W4390874160","https://openalex.org/W4391759936","https://openalex.org/W4401416243","https://openalex.org/W4402726938","https://openalex.org/W4404612908","https://openalex.org/W6745537798","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6802366246","https://openalex.org/W6810080435","https://openalex.org/W6850503672","https://openalex.org/W6852884379","https://openalex.org/W6853054754","https://openalex.org/W6854929498"],"related_works":["https://openalex.org/W3049557657","https://openalex.org/W3150915502","https://openalex.org/W8302103","https://openalex.org/W2111158727","https://openalex.org/W1809059965","https://openalex.org/W2024668666","https://openalex.org/W3171631314","https://openalex.org/W2155287816","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"Recent":[0],"works":[1,24],"have":[2,25,166],"shown":[3,167],"that":[4,168,210],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"can":[9,241],"facilitate":[10],"the":[11,45,125,139,142,211,236,245],"grounding":[12],"of":[13,47,79,117,191,199,207,214],"instructions":[14],"for":[15,90,160],"robotic":[16,162],"task":[17,163,182,212],"planning.":[18,164],"Despite":[19],"this":[20,40,61],"progress,":[21],"most":[22,219],"existing":[23],"primarily":[26],"focused":[27],"on":[28,197,244],"utilizing":[29],"raw":[30],"images":[31,80],"to":[32,81,113,132,156],"aid":[33],"LLMs":[34],"in":[35,101,124,138,176,181,231],"understanding":[36],"environmental":[37],"information.":[38],"However,":[39],"approach":[41,67],"not":[42],"only":[43],"limits":[44],"scope":[46],"observation":[48],"but":[49],"also":[50],"typically":[51],"necessitates":[52],"extensive":[53],"multimodal":[54],"data":[55],"collection":[56],"and":[57,86,99,106,121,147,179,202,235],"large-scale":[58],"models.":[59],"In":[60],"paper,":[62],"we":[63,150],"propose":[64],"a":[65,91,152,188],"novel":[66],"called":[68],"Graph-based":[69],"Robotic":[70],"Instruction":[71],"Decomposer":[72],"(GRID),":[73],"which":[74],"leverages":[75],"scene":[76,84,126,143],"graphs":[77,102],"instead":[78],"perceive":[82],"global":[83],"information":[85],"iteratively":[87],"plan":[88],"subtasks":[89,115],"given":[92],"instruction.":[93],"Our":[94],"method":[95,170,186,230],"encodes":[96],"object":[97],"attributes":[98],"relationships":[100],"through":[103],"an":[104],"LLM":[105],"Graph":[107],"Attention":[108],"Networks,":[109],"integrating":[110],"instruction":[111],"features":[112],"predict":[114],"consisting":[116],"pre-defined":[118],"robot":[119],"actions":[120],"target":[122],"objects":[123,208],"graph.":[127,144],"This":[128],"strategy":[129],"enables":[130],"robots":[131],"acquire":[133],"semantic":[134],"knowledge":[135],"widely":[136],"observed":[137],"environment":[140],"from":[141],"To":[145],"train":[146],"evaluate":[148],"GRID,":[149],"establish":[151],"dataset":[153],"construction":[154],"pipeline":[155],"generate":[157],"synthetic":[158],"datasets":[159,198],"graph-based":[161],"Experiments":[165,195],"our":[169,185,229],"outperforms":[171],"GPT-4":[172],"by":[173,217],"over":[174],"25.4%":[175],"subtask":[177],"accuracy":[178,213],"43.6%":[180],"accuracy.":[183],"Moreover,":[184],"achieves":[187],"real-time":[189],"speed":[190],"0.11s":[192],"per":[193],"inference.":[194],"conducted":[196],"unseen":[200],"scenes":[201,203],"with":[204],"varying":[205],"numbers":[206],"demonstrate":[209],"GRID":[215],"declined":[216],"at":[218],"3.8%,":[220],"showcasing":[221],"its":[222],"robust":[223],"cross-scene":[224],"generalization":[225],"ability.":[226],"We":[227],"validate":[228],"both":[232],"physical":[233],"simulation":[234],"real":[237],"world.":[238],"More":[239],"details":[240],"be":[242],"found":[243],"project":[246],"page":[247],"https://jackyzengl.github.io/GRID.github.io/.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}